CN109164825A - A kind of independent navigation barrier-avoiding method and device for multi-rotor unmanned aerial vehicle - Google Patents
A kind of independent navigation barrier-avoiding method and device for multi-rotor unmanned aerial vehicle Download PDFInfo
- Publication number
- CN109164825A CN109164825A CN201810917692.4A CN201810917692A CN109164825A CN 109164825 A CN109164825 A CN 109164825A CN 201810917692 A CN201810917692 A CN 201810917692A CN 109164825 A CN109164825 A CN 109164825A
- Authority
- CN
- China
- Prior art keywords
- target
- aerial vehicle
- unmanned aerial
- independent navigation
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/107—Simultaneous control of position or course in three dimensions specially adapted for missiles
Abstract
The invention discloses a kind of independent navigation barrier-avoiding methods and device for multi-rotor unmanned aerial vehicle, enough accuracy is obtained using the sensor of the smallest sensor combinations and least cost, it realizes unmanned plane low cost independent navigation avoidance, solves the bottleneck problem that small drone is applied in electric power, agricultural industry.Pass through visual sensor at low cost small in size, the apparent ground object target of feature during acquisition inspection, it navigates unmanned plane self-position is obtained after image recognition processing, while obtaining relative distance using binocular ranging, solve the problems, such as the automated intelligent inspection under multi-rotor unmanned aerial vehicle complex environment.
Description
Technical field
The present invention relates to the avoidance fields of unmanned plane more particularly to a kind of independent navigation for multi-rotor unmanned aerial vehicle to keep away
Hinder method and device, passes through vision and radar sensor perception and avoiding obstacles in inspection flight course.
Background technique
The field of technical grade multi-rotor unmanned aerial vehicle market comparative maturity only has agricultural, power domain at present.With electric system
For, there are North China, northeast, East China, Central China, northwest and south totally 6 transprovincially area's power network in China at present, and 110kV's or more is defeated
Electric wire just has more than 50 ten thousand kilometers.If hardware facility, personnel's line walking cost are all counted in, annual maintenance cost is difficult to think about it.
This does not also include the data additional increase expense that factors such as complete, adverse circumstances do not influence.Traditional line walking mode, single line walking one
It, can only check 6-10 base shaft tower, and unmanned plane half an hour can complete；Cost, efficiency and safety can obtain greatly
Promotion.At present based on manually controlling, the flying experience of heavy dependence manipulator is intelligent for the application of power patrol unmanned machine
Degree is extremely low, and can encounter various environmental factors during inspection, seriously affects the stability of aircraft, accident happens occasionally.
For inspection process, wherein there are many barrier, and route is complicated, it usually needs crosses over mountain after mountain, if can accomplish automatic path planning
And independent navigation, routing inspection efficiency can be greatly improved.And the realization of above-mentioned function, unmanned plane is required to high-precision autonomous
Navigate barrier avoiding function.By visual sensor at low cost small in size, the apparent ground object target of feature during inspection is obtained, it will
Unmanned plane self-position is obtained after image recognition processing to navigate, while obtaining relative distance using binocular ranging, is solved more
Automated intelligent inspection problem under rotor wing unmanned aerial vehicle complex environment.
In flight course, since the drift of inertia device after long-distance flight can cause biggish navigation error, GPS
It is easy by electromagnetic interference, and optical imagery target seeker can be by identifying objects ahead, and passes through binocular ranging, so that it may really
Determine relative position, realization positions aircraft itself.This project is used for more rotors based on the above principles, by its core technology
The vision avoidance of unmanned plane.It is core that this project embedded high-speed realtime graphic, which detects identification technology, in conjunction with space product optics
And inertia combined guidance Detection Techniques, it is applied to civilian multi-rotor unmanned aerial vehicle avoidance.Utilize binocular parallax ranging, principle such as Fig. 3
It is shown.Final products: the standalone module of integrated vision, ranging and processing unit, standard interface does in manufacturer with mainstream unmanned plane.?
Power-line patrolling field, multi-rotor unmanned aerial vehicle need to solve the problems, such as during inspection navigation and avoidance under complex electromagnetic environment,
The principle for carrying out navigation and avoidance using optical image security is similar with cruise missile guidance.It is dry in strong electromagnetic firstly the need of solving
It realizes using visual sensor as core independent of the autonomous of GPS the position that itself is determined in the case where disturbing environment GPS failure
Positioning.Then binocular vision is used, identification and ranging, position of the barriers such as measure traverse line with respect to itself are carried out.Pass through volume
Small visual sensor at low cost obtains the apparent ground object target of feature during inspection, will obtain nothing after image recognition processing
Man-machine self-position navigates, while obtaining relative distance using binocular ranging, solves under multi-rotor unmanned aerial vehicle complex environment
Automated intelligent inspection problem.
Machine vision is the technology-oriented discipline for the vision system function that people and biology are simulated in research with computer, it is one
The comprehensive branch of learning, its purpose are the visual worlds for allowing computer that can perceive surrounding, understand its space composition and variation rule
Rule.Guidance unmanned plane is assisted to carry out target strike using video, it is the application in military field of machine vision, in unmanned plane
During using video vectored attack target, it would be desirable to according to the pixel coordinate in the picture of lock onto target in image, come
Guidance unmanned plane, which flies to, responds the target of locking, and it is exactly so-called world coordinate system that ground target, which is in geographic coordinate system,.
In traditional GPS autopilot navigation principle, after specified starting and the longitude and latitude point terminated, autopilot can be calculated
The course angle of beginning and end out, then autopilot can adjust the course of flight, be adjusted by closed loop PID, make the course of flight
Course angle is approached at angle always, and in the process real-time update course angle of flight.After locking and tracking target, how to guide
Unmanned plane will be a vital step close to simultaneously target of attack.
Summary of the invention
For the defects in the prior art, the object of the present invention is to provide a kind of independent navigations for multi-rotor unmanned aerial vehicle
Barrier-avoiding method and device solve the problems, such as existing multi-rotor unmanned aerial vehicle automatic sensing and avoiding obstacles.
The present invention is realized according to following technical scheme:
A kind of independent navigation barrier-avoiding method for multi-rotor unmanned aerial vehicle, which comprises the steps of:
Step S1: the atural object and obstacle target optical imagery for being fixed on aircraft front end camera are obtained, in image
Target detected, extracted, identified and tracked, obtain Angle Position deviation of the target relative to aircraft height azimuth axis；
Step S2: the information of the angle of deviation combination inertial sensor of target relative flight device is coordinately transformed, simultaneously
The geographical coordinate that three features above points of ground target are obtained by GIS-Geographic Information System is resolved using information above forming position
Equation finally calculates posture and the position of aircraft；
Step S3: rectifying a deviation according to preset flight path of the position of derivation to aircraft, controls aircraft according to correct side
To flight, when close to barrier, binocular sensor absorbs target image simultaneously, using in binocular parallax measurement two images
The distance of same target relative flight device, when distance value is less than safe distance, aircraft adjusts posture change of flight direction, directly
To avoiding obstacles.
In above-mentioned technical proposal, the method also includes step S4: when encountering transparent glass wall in flight course,
It needs to install ultrasonic sensor additional in independent navigation obstacle avoidance system and be backed up, before binocular vision sensor can not detect
When square barrier, unmanned aerial vehicle (UAV) control circuit is entered using ultrasonic signal as measuring signal.
In above-mentioned technical proposal, the load-carrying of the unmanned plane at 3 kilograms or more, the barrier include tiny branch or
Electrical lead.
In above-mentioned technical proposal, when the unmanned plane high speed flight, by high speed embedded vision chip to great amount of images
Data are handled, treatment process include high-resolution binocular image data are pre-processed, target detection, tracking, improve
Independent navigation obstacle avoidance system is to the reaction speed of barrier and the real-time of control loop.
A kind of independent navigation obstacle avoidance system for multi-rotor unmanned aerial vehicle of the invention, which is characterized in that passed including vision
Sensor cell, images match processing unit, environment relative information processing module, carrier self information processing module, the vision
Sensor unit is connect with described image matching treatment unit, and described image matching treatment unit is opposite with the environment respectively to be believed
Processing module and carrier self information processing module connection are ceased, wherein
The image shape and gray feature of far and near target in the visual sensor unit acquisition flying scene, after being supplied to
Continuous image operation and processing unit, carry out target detection and extraction；
Described image matching treatment unit, visual sensor acquired image gray scale and shape information are filtered,
Transformation and extraction, detect the relative position of scenery in image, and carry out continuing tracking to target in subsequent image sequence；
The environment relative information processing module is carried out by the parallax of identical scenery in binocular image in conjunction with image coordinate
Solid, which resolves, obtains relative distance information, real-time transmission to judgement and control unit, driving unmanned plane movement；
The carrier self information processing module controls access control loop by the judgement signal, judges subtracting for unmanned plane
Speed, direction adjustment.
In above-mentioned technical proposal, the visual sensor unit uses binocular vision processing unit, at the binocular vision
It manages unit and target tiny and with texture is detected by binocular camera, relative distance is measured by binocular parallax.
In above-mentioned technical proposal, the system also includes millimetre-wave radar unit, the millimetre-wave radar unit is for visiting
It surveys that transparent, light is poor or uses in the case where no corner characteristics, measures target relative distance, obtain corresponding avoidance information, and
The visual sensor unit matching uses.
In above-mentioned technical proposal, the unmanned plane uses the independent navigation obstacle avoidance system using vision as core, guarantees inspection
Reliability in flight course, avoids unmanned aerial vehicle to electrical lead.
Compared with prior art, the present invention have it is following the utility model has the advantages that
The present invention greatly improves the safety of unmanned plane；And the intelligence of unmanned plane, the degree of automation are greatly improved, greatly
Width mitigates the manipulation pressure for flying hand；The present invention can also greatly improve unmanned plane to the adaptability of environment, expand in agricultural, electric power
The application convenience and work capacity in equal fields.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is the schematic diagram of tracker locking tracking target；
Fig. 2 is the side schematic view of unmanned plane pitch angle；
Fig. 3 is the side schematic view of unmanned plane yaw angle；
Fig. 4 is the schematic diagram of tracker locking tracking target；
Fig. 5 is the schematic diagram of unmanned plane vision guided navigation；
Fig. 6 is binocular range measurement principle figure.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection scope.
A kind of independent navigation barrier-avoiding method for multi-rotor unmanned aerial vehicle of the invention, which is characterized in that including walking as follows
It is rapid:
Step S1: the atural object and obstacle target optical imagery for being fixed on aircraft front end camera are obtained, in image
Target detected, extracted, identified and tracked, obtain Angle Position deviation of the target relative to aircraft height azimuth axis, such as
The schematic diagram of the target of tracker locking tracking shown in Fig. 1；
Step S2: the information of the angle of deviation combination inertial sensor of target relative flight device is coordinately transformed, simultaneously
The geographical coordinate that three features above points of ground target are obtained by GIS-Geographic Information System is resolved using information above forming position
Equation, finally calculates posture and the position of aircraft, realizes the independent navigation for not depending on GPS, as shown in Figure 5 as unmanned plane
The schematic diagram of vision guided navigation；In image-guidance mode, camera is functionally equivalent to a video camera.Space any point S
Imaging position on video camera can use pin hole (pinhole) imaging model approximate representation.In actual camera, the plane of delineation
The position of f (focal length) behind projection centre, projected image is to stand upside down, in order to avoid this inverted image, it is assumed that projection is flat
Face is located at before projection centre.Ignore seeker optical system nonlinear influencing factors, linear camera model can be used
The imaging system for describing airborne camera relates generally to following 3 coordinate systems: scene coordinate system (Xw, Yw, Zw), also referred to as absolutely
To coordinate system or world coordinate system, for indicating the absolute coordinate of scene point (or landmark point), setting OXwZw and local ground in figure
Plane is parallel, and sets OZw, parallel with the directional velocity in the error free situation of unmanned plane；Camera coordinate system (Xc, Yc, Zc),
Centered on video camera, the data mode that scene point can be expressed as centered on video camera；Pixel coordinate system (u, v) indicates
Imaging position (pixel as unit of) of the scene point in camera focal plane arrays (FPA) is two-dimensional coordinate system.
As shown in Figure 1, first with the target of video tracker output and the deviation of target center, it can be seen that target
Point deviation dy away from target center vertical direction away from target center deviation dx in the horizontal direction and target point.
Assuming that the roll angle where unmanned plane is φ at this time, pitch angle is θ and yaw angle is ψ, wherein roll angle is φ, bows
The elevation angle is that θ can use the sensor real-time measurement on unmanned plane, and yaw angle is that ψ is unknown, eliminates the influence of roll angle φ, makes figure
As handling as follows within a horizontal plane:
If in the process entirely tracked, it is FOV that we obtain camera field angle at any time, if our video sources are
Pal video, then yaw angle at this time, which can be calculated, isTherefore roll angle φ, pitching angle theta at this time
It is known with yaw angle ψ.
As shown in Fig. 2, just being needed in order to which the corresponding target point in ground in image is moved to the corresponding ground point location of target center
Adjust the posture of unmanned plane；As can be known from Fig. 3, calculate ground target select floor projection to target center accordingly millet cake distance
DY can be calculated according to dX/DY=dx '/dy ' in dX, therefore can be evaluated whether the height k of next destination1.According to unmanned plane
The current longitude and latitude returned has calculated angle of drift ψ, therefore can calculate the next of unmanned plane during flying in the telegoniometer of angle of drift
The height h of a destination essence latitude and next destination1, such unmanned plane is just always towards goal directed flight.
Step S3: rectifying a deviation according to preset flight path of the position of derivation to aircraft, controls aircraft according to correct side
To flight, when close to barrier, binocular sensor absorbs target image simultaneously, using in binocular parallax measurement two images
The distance of same target relative flight device flies control whole posture change of flight direction when distance value is less than safe distance, until
Avoiding obstacles.
Backup measurement is added when the binocular vision sensor fails, the invention also includes step S4: in flight course
When encountering transparent glass wall, needs to install ultrasonic sensor additional in independent navigation obstacle avoidance system and be backed up, in binocular
When visual sensor can not detect front obstacle, unmanned aerial vehicle (UAV) control is entered using MMW RADAR SIGNAL USING as measuring signal and is returned
Road.
The load-carrying of unmanned plane is mainly used for electric inspection process, environmental monitoring, safety monitoring and agricultural spray at 3 kilograms or more
Field, barrier include tiny branch or electrical lead.
When unmanned plane high speed flight, great amount of images data are handled, improve independent navigation obstacle avoidance system to obstacle
The reaction speed of object and the real-time of control loop.
Volume shared by unmanned plane independent navigation obstacle avoidance system, weight, power consumption are strict with, and the load of excessive aircraft is not take up
And the energy, ensure unmanned plane operating efficiency.
Unmanned plane cruise duration the multi-rotor unmanned aerial vehicle at 40 minutes or more, carry photoelectric nacelle or optical spectrum imagers etc
Load, the main transmission line of electricity more than inspection 500KV, and need to see conducting wire or tower bar in detail in closer distance
It examines, it is therefore desirable to consider under complicated electromagnetic interference environment, use the complex navigation obstacle avoidance module using vision as core, guarantee to patrol
The reliability in flight course is examined, avoids unmanned aerial vehicle to electrical lead, and causes greater loss.
Fig. 4 be tracker locking tracking target schematic diagram, as shown in figure 4, one kind of the invention for more rotors nobody
The independent navigation obstacle avoidance system of machine, which is characterized in that opposite including visual sensor unit, images match processing unit, environment
Message processing module, carrier self information processing module, the visual sensor unit and described image matching treatment unit connect
It connects, described image matching treatment unit is handled with the environment relative information processing module and the carrier self information respectively
Module connection, wherein
The image shape and gray feature of far and near target in the visual sensor unit acquisition flying scene, after being supplied to
Continuous image operation and processing unit, carry out target detection and extraction；
Described image matching treatment unit, visual sensor acquired image gray scale and shape information are filtered,
Transformation and extraction, detect the relative position of scenery in image, and carry out continuing tracking to target in subsequent image sequence；
The environment relative information processing module is carried out by the parallax of identical scenery in binocular image in conjunction with image coordinate
Solid, which resolves, obtains relative distance information, real-time transmission to judgement and control unit, driving unmanned plane movement；
The carrier self information processing module controls access control loop by the judgement signal, judges subtracting for unmanned plane
Speed, direction adjustment.
Visual sensor unit of the invention uses binocular vision processing unit, and the binocular vision processing unit is by binocular
Camera detects target tiny and with texture, measures relative distance by binocular parallax, principle is as shown in Fig. 6.Binocular
Stereoscopic vision (Binocular Stereo Vision) is a kind of important form of machine vision, it is based on right and left eyes parallax
Principle simultaneously utilizes two images of the imaging device from different position acquisition testees, by calculating the position between image corresponding points
Deviation is set, the method to obtain object dimensional geological information.It merges the image of two eyes acquisition and observes the difference between them
Not (anaglyph) allows us to obtain apparent sense of depth, establishes the corresponding relationship between feature, by the same space physical points
Photosites in different images are mapped.Binocular stereo vision measurement method is with high-efficient, precision is suitable, system structure
Simply, the advantages that at low cost, is very suitable for online, non-contact product testing and the quality control at manufacture scene.To moving object
In body (including animal and human body body) measurement, since image acquisition was completed in moment, Stereo Vision is one
The more effective measurement method of kind.Binocular Stereo Vision System is one of key technology of computer vision, obtains space three-dimensional field
The range information of scape is also most basic content in computer vision research.
The invention also includes millimetre-wave radar unit, the millimetre-wave radar unit for detect transparent, light it is poor or
It is used in the case where no corner characteristics, measures target relative distance, obtain corresponding avoidance information and the visual sensor unit
It is used cooperatively.
Unmanned plane of the invention uses the independent navigation obstacle avoidance system using vision as core, guarantees in inspection flight course
Reliability avoids unmanned aerial vehicle to electrical lead.
Obstacle avoidance apparatus for multi-rotor unmanned aerial vehicle of the invention solves more rotor plant protection or patrol unmanned machine independent navigation
Avoidance problem.Enough accuracy is obtained using the sensor of the smallest sensor combinations and least cost, realizes unmanned plane low cost
Independent navigation avoidance solves the bottleneck problem that small drone is applied in electric power, agricultural industry.Pass through view at low cost small in size
Feel sensor, obtain the apparent ground object target of feature during inspection, unmanned plane self-position will be obtained after image recognition processing
It navigates, while obtaining relative distance using binocular ranging, the automated intelligent solved under multi-rotor unmanned aerial vehicle complex environment patrols
Inspection problem.
In flight course, since the drift of inertia device after long-distance flight can cause biggish navigation error, GPS
It is easy by electromagnetic interference, and optical imagery target seeker can be by identifying objects ahead, and passes through binocular ranging, so that it may really
Determine relative position, realization positions aircraft itself.This project is used for more rotors based on the above principles, by its core technology
The vision avoidance of unmanned plane.It is core that this project embedded high-speed realtime graphic, which detects identification technology, in conjunction with space product optics
And inertia combined guidance Detection Techniques, it is applied to civilian multi-rotor unmanned aerial vehicle avoidance.
Final products: the standalone module of integrated vision, ranging and processing unit does standard with mainstream unmanned plane manufacturer and connects
Mouthful.In power-line patrolling field, multi-rotor unmanned aerial vehicle needs to solve during inspection navigation and avoidance under complex electromagnetic environment
Problem, the principle for carrying out navigation and avoidance using optical image security are similar with cruise missile guidance.Firstly the need of solution strong
Electromagnetic interference environment GPS determines the position of itself in the case where failing, using visual sensor as core, realize independent of GPS
Autonomous positioning.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow
Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (8)
1. a kind of independent navigation barrier-avoiding method for multi-rotor unmanned aerial vehicle, which comprises the steps of:
Step S1: the atural object and obstacle target optical imagery for being fixed on aircraft front end camera are obtained, to the mesh in image
Mark is detected, is extracted, identified and is tracked, and Angle Position deviation of the target relative to aircraft height azimuth axis is obtained；
Step S2: the information of the angle of deviation combination inertial sensor of target relative flight device is coordinately transformed, is passed through simultaneously
GIS-Geographic Information System obtains the geographical coordinate of three features above points of ground target, utilizes information above forming position resolving side
Journey finally calculates posture and the position of aircraft；
Step S3: rectifying a deviation according to preset flight path of the position of derivation to aircraft, and control aircraft flies according to correct direction
Row, when close to barrier, binocular sensor absorbs target image simultaneously, is measured using binocular parallax same in two images
The distance of target relative flight device, when distance value is less than safe distance, aircraft adjusts posture change of flight direction, until keeping away
Open barrier.
2. the independent navigation barrier-avoiding method according to claim 1 for multi-rotor unmanned aerial vehicle, which is characterized in that the side
Method further includes step S4: when encountering transparent glass wall in flight course, needing to install additional in independent navigation obstacle avoidance system
Millimetre-wave radar sensor is backed up, when binocular vision sensor can not detect front obstacle, with ultrasonic signal
Enter unmanned aerial vehicle (UAV) control circuit as measuring signal.
3. the barrier-avoiding method according to claim 1 or 2 suitable for multi-rotor unmanned aerial vehicle, which is characterized in that the nothing
At 3 kilograms or more, the barrier includes tiny branch or electrical lead for man-machine load-carrying.
4. the barrier-avoiding method according to claim 1 or 2 suitable for multi-rotor unmanned aerial vehicle, which is characterized in that the nothing
When man-machine high speed flight, great amount of images data are handled by high speed embedded vision chip, treatment process includes to height
Resolution ratio binocular image data are pre-processed, target detection, tracking, improve reaction of the independent navigation obstacle avoidance system to barrier
The real-time of speed and control loop.
5. a kind of independent navigation obstacle avoidance system for multi-rotor unmanned aerial vehicle, which is characterized in that including visual sensor unit, figure
As matching treatment unit, environment relative information processing module, carrier self information processing module, the visual sensor unit with
Described image matching treatment unit connection, described image matching treatment unit respectively with the environment relative information processing module with
And the carrier self information processing module connection, wherein
The image shape and gray feature of far and near target, are supplied to subsequent figure in the visual sensor unit acquisition flying scene
As operation and processing unit, target detection and extraction are carried out；
Described image matching treatment unit, is filtered visual sensor acquired image gray scale and shape information, converts
And extraction, detect the relative position of scenery in image, and carry out continuing tracking to target in subsequent image sequence；
The environment relative information processing module is carried out three-dimensional by the parallax of identical scenery in binocular image in conjunction with image coordinate
It resolves and obtains relative distance information, real-time transmission to judgement and control unit, driving unmanned plane movement；
The carrier self information processing module by the judgement signal control access control loop, judge unmanned plane deceleration,
Direction adjustment.
6. the independent navigation obstacle avoidance system according to claim 5 for multi-rotor unmanned aerial vehicle, which is characterized in that the view
Feel that sensor unit uses binocular vision processing unit, the binocular vision processing unit is detected tiny by binocular camera and had
Textured target measures relative distance by binocular parallax.
7. the independent navigation obstacle avoidance system according to claim 6 for multi-rotor unmanned aerial vehicle, which is characterized in that the system
System further includes millimetre-wave radar unit, and transparent, light is poor or feelings in no corner characteristics for detecting for the millimetre-wave radar unit
It is used under condition, measures target relative distance, obtained corresponding avoidance information and the visual sensor unit matching uses.
8. the independent navigation obstacle avoidance system according to claim 6 for multi-rotor unmanned aerial vehicle, which is characterized in that the nothing
The man-machine independent navigation obstacle avoidance system used using vision as core guarantees the reliability in inspection flight course, avoids unmanned plane
Hit electrical lead.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810917692.4A CN109164825A (en) | 2018-08-13 | 2018-08-13 | A kind of independent navigation barrier-avoiding method and device for multi-rotor unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810917692.4A CN109164825A (en) | 2018-08-13 | 2018-08-13 | A kind of independent navigation barrier-avoiding method and device for multi-rotor unmanned aerial vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109164825A true CN109164825A (en) | 2019-01-08 |
Family
ID=64895747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810917692.4A Pending CN109164825A (en) | 2018-08-13 | 2018-08-13 | A kind of independent navigation barrier-avoiding method and device for multi-rotor unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109164825A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110794854A (en) * | 2019-11-27 | 2020-02-14 | 陈会强 | Autonomous take-off and landing method for fixed-wing unmanned aerial vehicle |
| CN111487997A (en) * | 2020-05-12 | 2020-08-04 | 西安爱生技术集团公司 | Double-machine cooperative guidance method for attack type unmanned aerial vehicle |
| CN111739050A (en) * | 2020-08-05 | 2020-10-02 | 北京控制与电子技术研究所 | Zynq-based aircraft navigation system for attitude measurement and celestial body centroid extraction |
| CN111813142A (en) * | 2019-07-18 | 2020-10-23 | 中国石油化工股份有限公司 | Unmanned aerial vehicle autonomous obstacle avoidance control method for crude oil pipeline inspection |
| CN113110567A (en) * | 2021-03-05 | 2021-07-13 | 广州大学 | Unmanned aerial vehicle-based building appearance surveying method, device, equipment and medium |
| CN113678082A (en) * | 2019-03-25 | 2021-11-19 | 索尼集团公司 | Mobile body, control method for mobile body, and program |
| CN114371720A (en) * | 2021-12-29 | 2022-04-19 | 国家电投集团贵州金元威宁能源股份有限公司 | Control method and control device for unmanned aerial vehicle to track target |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5581250A (en) * | 1995-02-24 | 1996-12-03 | Khvilivitzky; Alexander | Visual collision avoidance system for unmanned aerial vehicles |
| CN105021184A (en) * | 2015-07-08 | 2015-11-04 | 西安电子科技大学 | Pose estimation system and method for visual carrier landing navigation on mobile platform |
| CN105335733A (en) * | 2015-11-23 | 2016-02-17 | 西安韦德沃德航空科技有限公司 | Autonomous landing visual positioning method and system for unmanned aerial vehicle |
| CN106204443A (en) * | 2016-07-01 | 2016-12-07 | 成都通甲优博科技有限责任公司 | A kind of panorama UAS based on the multiplexing of many mesh |
| CN106352897A (en) * | 2016-08-26 | 2017-01-25 | 杨百川 | Silicon MEMS (micro-electromechanical system) gyroscope error estimating and correcting method based on monocular visual sensor |
| US20170371353A1 (en) * | 2016-06-23 | 2017-12-28 | Qualcomm Incorporated | Automatic Tracking Mode For Controlling An Unmanned Aerial Vehicle |
| CN107656545A (en) * | 2017-09-12 | 2018-02-02 | 武汉大学 | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid |
| CN107677274A (en) * | 2017-09-12 | 2018-02-09 | 西北工业大学 | Unmanned plane independent landing navigation information real-time resolving method based on binocular vision |
| CN108054453A (en) * | 2017-12-28 | 2018-05-18 | 南京工程学院 | A kind of power-line patrolling unmanned plane charging method |
| CN108139758A (en) * | 2015-10-09 | 2018-06-08 | 深圳市大疆创新科技有限公司 | Apparatus of transport positioning based on significant characteristics |
| CN108351649A (en) * | 2015-09-15 | 2018-07-31 | 深圳市大疆创新科技有限公司 | System and method for UAV interactive instructions and control |
| CN108364003A (en) * | 2018-04-28 | 2018-08-03 | 国网河南省电力公司郑州供电公司 | The electric inspection process method and device merged based on unmanned plane visible light and infrared image |
-
2018
- 2018-08-13 CN CN201810917692.4A patent/CN109164825A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5581250A (en) * | 1995-02-24 | 1996-12-03 | Khvilivitzky; Alexander | Visual collision avoidance system for unmanned aerial vehicles |
| CN105021184A (en) * | 2015-07-08 | 2015-11-04 | 西安电子科技大学 | Pose estimation system and method for visual carrier landing navigation on mobile platform |
| CN108351649A (en) * | 2015-09-15 | 2018-07-31 | 深圳市大疆创新科技有限公司 | System and method for UAV interactive instructions and control |
| CN108139758A (en) * | 2015-10-09 | 2018-06-08 | 深圳市大疆创新科技有限公司 | Apparatus of transport positioning based on significant characteristics |
| CN105335733A (en) * | 2015-11-23 | 2016-02-17 | 西安韦德沃德航空科技有限公司 | Autonomous landing visual positioning method and system for unmanned aerial vehicle |
| US20170371353A1 (en) * | 2016-06-23 | 2017-12-28 | Qualcomm Incorporated | Automatic Tracking Mode For Controlling An Unmanned Aerial Vehicle |
| CN106204443A (en) * | 2016-07-01 | 2016-12-07 | 成都通甲优博科技有限责任公司 | A kind of panorama UAS based on the multiplexing of many mesh |
| CN106352897A (en) * | 2016-08-26 | 2017-01-25 | 杨百川 | Silicon MEMS (micro-electromechanical system) gyroscope error estimating and correcting method based on monocular visual sensor |
| CN107656545A (en) * | 2017-09-12 | 2018-02-02 | 武汉大学 | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid |
| CN107677274A (en) * | 2017-09-12 | 2018-02-09 | 西北工业大学 | Unmanned plane independent landing navigation information real-time resolving method based on binocular vision |
| CN108054453A (en) * | 2017-12-28 | 2018-05-18 | 南京工程学院 | A kind of power-line patrolling unmanned plane charging method |
| CN108364003A (en) * | 2018-04-28 | 2018-08-03 | 国网河南省电力公司郑州供电公司 | The electric inspection process method and device merged based on unmanned plane visible light and infrared image |
Non-Patent Citations (3)
| Title |
|---|
| 王亭亭等: "小型无人机立体视觉目标追踪定位方法", 《电光与控制》 * |
| 都伊林: "《智能安防新发展与应用》", 31 May 2018 * |
| 金刚石等: "基于坐标变换的视频跟踪误差角的计算方法", 《激光与红外》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113678082A (en) * | 2019-03-25 | 2021-11-19 | 索尼集团公司 | Mobile body, control method for mobile body, and program |
| CN111813142A (en) * | 2019-07-18 | 2020-10-23 | 中国石油化工股份有限公司 | Unmanned aerial vehicle autonomous obstacle avoidance control method for crude oil pipeline inspection |
| CN110794854A (en) * | 2019-11-27 | 2020-02-14 | 陈会强 | Autonomous take-off and landing method for fixed-wing unmanned aerial vehicle |
| CN111487997A (en) * | 2020-05-12 | 2020-08-04 | 西安爱生技术集团公司 | Double-machine cooperative guidance method for attack type unmanned aerial vehicle |
| CN111739050A (en) * | 2020-08-05 | 2020-10-02 | 北京控制与电子技术研究所 | Zynq-based aircraft navigation system for attitude measurement and celestial body centroid extraction |
| CN111739050B (en) * | 2020-08-05 | 2020-11-20 | 北京控制与电子技术研究所 | Zynq-based aircraft navigation system for attitude measurement and celestial body centroid extraction |
| CN113110567A (en) * | 2021-03-05 | 2021-07-13 | 广州大学 | Unmanned aerial vehicle-based building appearance surveying method, device, equipment and medium |
| CN114371720A (en) * | 2021-12-29 | 2022-04-19 | 国家电投集团贵州金元威宁能源股份有限公司 | Control method and control device for unmanned aerial vehicle to track target |
| CN114371720B (en) * | 2021-12-29 | 2023-09-29 | 国家电投集团贵州金元威宁能源股份有限公司 | Control method and control device for realizing tracking target of unmanned aerial vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109164825A (en) | A kind of independent navigation barrier-avoiding method and device for multi-rotor unmanned aerial vehicle | |
| US20220124303A1 (en) | Methods and systems for selective sensor fusion | |
| CN110446159B (en) | System and method for accurate positioning and autonomous navigation of indoor unmanned aerial vehicle | |
| CN111958592B (en) | Image semantic analysis system and method for transformer substation inspection robot | |
| CN104298248B (en) | Rotor wing unmanned aerial vehicle accurate vision positioning and orienting method | |
| CN104215239B (en) | Guidance method using vision-based autonomous unmanned plane landing guidance device | |
| CN109683629B (en) | Unmanned aerial vehicle electric power overhead line system based on combination navigation and computer vision | |
| CN107703951B (en) | A kind of unmanned plane barrier-avoiding method and system based on binocular vision | |
| CN105759829A (en) | Laser radar-based mini-sized unmanned plane control method and system | |
| CN105182992A (en) | Unmanned aerial vehicle control method and device | |
| US20200191556A1 (en) | Distance mesurement method by an unmanned aerial vehicle (uav) and uav | |
| CN107144281B (en) | Unmanned aerial vehicle indoor positioning system and positioning method based on cooperative targets and monocular vision | |
| CN109885084A (en) | A kind of multi-rotor unmanned aerial vehicle Autonomous landing method based on monocular vision and fuzzy control | |
| Bao et al. | Vision-based horizon extraction for micro air vehicle flight control | |
| CN109282808A (en) | Unmanned plane and Multi-sensor Fusion localization method for the detection of bridge Cut-fill | |
| US10921825B2 (en) | System and method for perceptive navigation of automated vehicles | |
| CN108733064A (en) | A kind of the vision positioning obstacle avoidance system and its method of unmanned plane | |
| Bian et al. | A point-line-based SLAM framework for UAV close proximity transmission tower inspection | |
| Celik et al. | Mono-vision corner SLAM for indoor navigation | |
| CN115880368A (en) | Method and system for detecting obstacle of power grid inspection unmanned aerial vehicle and storage medium | |
| CN112859923B (en) | Unmanned aerial vehicle vision formation flight control system | |
| Denuelle et al. | A sparse snapshot-based navigation strategy for UAS guidance in natural environments | |
| CN105959529B (en) | It is a kind of single as method for self-locating and system based on panorama camera | |
| CN110068827A (en) | A kind of method of the autonomous object ranging of unmanned plane | |
| Jingjing et al. | Research on autonomous positioning method of UAV based on binocular vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190108 |